Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    statements expressing certainty or strong opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actually
    -0.99
    actually
    -0.90
     faktisk
    -0.84
     perhaps
    -0.83
     Actually
    -0.82
    Actually
    -0.81
     maybe
    -0.80
     faktiskt
    -0.79
     apparently
    -0.78
    竟然
    -0.74
    POSITIVE LOGITS
     ब्रेकडाउन
    0.74
    GEBURTSDATUM
    0.65
    OGND
    0.63
     plenty
    0.62
     transfieras
    0.61
    Tembelea
    0.60
     Drapeau
    0.57
    plenty
    0.57
    UnknownFieldSet
    0.57
     ProtoMessage
    0.55
    Act Density 0.320%

    No Known Activations